{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T06:12:24Z","timestamp":1765260744417,"version":"3.46.0"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T00:00:00Z","timestamp":1757894400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T00:00:00Z","timestamp":1757894400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100024250","name":"Israel Innovation Authority","doi-asserted-by":"publisher","award":["78533","78533"],"award-info":[{"award-number":["78533","78533"]}],"id":[{"id":"10.13039\/501100024250","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Lang Resources &amp; Evaluation"],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1007\/s10579-025-09863-y","type":"journal-article","created":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T03:43:50Z","timestamp":1757907830000},"page":"3889-3909","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Building a specialised Hebrew textual corpus on construction, planning and architecture"],"prefix":"10.1007","volume":"59","author":[{"given":"Omri","family":"Shafer-Raviv","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6777-5228","authenticated-orcid":false,"given":"Or","family":"Aleksandrowicz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nick","family":"Howell","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Rosenberg","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,9,15]]},"reference":[{"key":"9863_CR1","unstructured":"About The Center (2024). Retrieved from https:\/\/curs.net.technion.ac.il\/en\/the-center\/"},{"key":"9863_CR2","unstructured":"About the Ministry (2022). Retrieved from https:\/\/www.gov.il\/en\/departments\/about\/about_moch"},{"key":"9863_CR3","unstructured":"About the Ministry of Environmental Protection (2024). Retrieved from https:\/\/www.gov.il\/en\/departments\/about\/about_us"},{"key":"9863_CR4","unstructured":"About the National Building Research Institute (2024). Retrieved from https:\/\/nbri.net.technion.ac.il\/en\/about\/"},{"key":"9863_CR5","unstructured":"Aleksandrowicz, O., Rosenberg, D., Shafer-Raviv, Omri, & Ordan, N. (2024). Hebrew textual corpus on construction, planning, and architecture. Retrieved from GitHUB. https:\/\/github.com\/bdar-lab\/heb_architecture_corpus"},{"issue":"94","key":"9863_CR6","doi-asserted-by":"publisher","first-page":"129","DOI":"10.22210\/suvlin.2022.094.01","volume":"48","author":"K Bogeti\u0107","year":"2022","unstructured":"Bogeti\u0107, K., Batanovi\u0107, V., & Ljube\u0161i\u0107, N. (2022). Corpus compilation for digital humanities in lower\u2013resourced languages: A practical look at compiling thematic digital media corpora in serbian, Croatian and Slovenian. Suvremena Lingvistika, 48(94), 129\u2013152. https:\/\/doi.org\/10.22210\/suvlin.2022.094.01","journal-title":"Suvremena Lingvistika"},{"issue":"2","key":"9863_CR7","doi-asserted-by":"publisher","first-page":"632","DOI":"10.1177\/0739456X21995890","volume":"44","author":"C Brinkley","year":"2021","unstructured":"Brinkley, C., & Stahmer, C. (2021). What is in a plan? Using natural Language processing to read 461 California City general plans. Journal of Planning Education and Research, 44(2), 632\u2013648. https:\/\/doi.org\/10.1177\/0739456X21995890","journal-title":"Journal of Planning Education and Research"},{"issue":"3","key":"9863_CR8","doi-asserted-by":"publisher","first-page":"e06322","DOI":"10.1016\/j.heliyon.2021.e06322","volume":"7","author":"M Cai","year":"2021","unstructured":"Cai, M. (2021). Natural Language processing for urban research: A systematic review. Heliyon, 7(3), e06322. https:\/\/doi.org\/10.1016\/j.heliyon.2021.e06322","journal-title":"Heliyon"},{"key":"9863_CR9","unstructured":"Cheng, W. (2014). Corpus analyses of professional discourse. In V. Bhatia, & S. Bremner (Eds.), The Routledge handbook of Language and professional communication. Routledge."},{"key":"9863_CR10","unstructured":"DellaPergola, S. (2020). Diaspora vs. Homeland: Development, unemployment and ethnic migration to israel, 1991\u20132019 (Vol. 31). The Avraham Harman Institute of Contemporary Jewry, the Hebrew University of Jerusalem."},{"key":"9863_CR11","doi-asserted-by":"publisher","first-page":"104169","DOI":"10.1016\/j.autcon.2022.104169","volume":"136","author":"Y Ding","year":"2022","unstructured":"Ding, Y., Ma, J., & Luo, X. (2022). Applications of natural Language processing in construction. Automation in Construction, 136, 104169. https:\/\/doi.org\/10.1016\/j.autcon.2022.104169","journal-title":"Automation in Construction"},{"key":"9863_CR12","doi-asserted-by":"crossref","unstructured":"Egbert, J., Biber, D., & Gray, B. (2022). Designing and evaluating Language corpora: A practical framework for corpus representativeness. Cambridge University Press.","DOI":"10.1017\/9781316584880"},{"key":"9863_CR13","doi-asserted-by":"crossref","unstructured":"Flowerdew, L. (2004). The argument for using english specialized corpora to understand academic and professional Language. In Ulla, Connor, & T. A. Upton (Eds.), Discourse in the professions: Perspectives from corpus linguistics (pp. 11\u201333). John Benjamins.","DOI":"10.1075\/scl.16.02flo"},{"issue":"3","key":"9863_CR14","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1177\/08854122241229571","volume":"39","author":"X Fu","year":"2024","unstructured":"Fu, X. (2024). Natural Language processing in urban planning: A research agenda. Journal of Planning Literature, 39(3), 395\u2013407. https:\/\/doi.org\/10.1177\/08854122241229571","journal-title":"Journal of Planning Literature"},{"issue":"3","key":"9863_CR15","doi-asserted-by":"publisher","first-page":"525","DOI":"10.1080\/01944363.2023.2271893","volume":"90","author":"X Fu","year":"2023","unstructured":"Fu, X., Wang, R., & Li, C. (2023). Can ChatGPT evaluate plans?? Journal of the American Planning Association, 90(3), 525\u2013536. https:\/\/doi.org\/10.1080\/01944363.2023.2271893","journal-title":"Journal of the American Planning Association"},{"key":"9863_CR16","unstructured":"Fuchs, S., & Amor, R. (2021). Natural Language Processing for Building Code Interpretation: A Systematic Literature Review. Paper presented at the 38th International Conference of CIB W78, Luxembourg."},{"key":"9863_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.esp.2018.02.002","volume":"51","author":"A Gilmore","year":"2018","unstructured":"Gilmore, A., & Millar, N. (2018). The Language of civil engineering research articles: A corpus-based approach. English for Specific Purposes, 51, 1\u201317. https:\/\/doi.org\/10.1016\/j.esp.2018.02.002","journal-title":"English for Specific Purposes"},{"key":"9863_CR18","doi-asserted-by":"crossref","unstructured":"Goldin, G., Howell, N., Ordan, N., Rabinovich, E., & Wintner, S. (2024). The Knesset Corpus: An Annotated Corpus of Hebrew Parliamentary Proceedings.","DOI":"10.21203\/rs.3.rs-4480984\/v1"},{"issue":"3","key":"9863_CR19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.rmal.2024.100146","volume":"3","author":"L Goulart","year":"2024","unstructured":"Goulart, L., Staples, Shelley, Novikov, Aleksey, Picoral, A., & Reppen, R. (2024). An introduction to CIABATTA: Increasing accessibility to corpus creation for non-experts. Research Methods in Applied Linguistics, 3(3), 1\u20138. https:\/\/doi.org\/10.1016\/j.rmal.2024.100146","journal-title":"Research Methods in Applied Linguistics"},{"issue":"3","key":"9863_CR20","doi-asserted-by":"publisher","first-page":"380","DOI":"10.1075\/ijcl.17.3.04har","volume":"17","author":"A Hardie","year":"2012","unstructured":"Hardie, A. (2012). CQPweb - combining power, flexibility and usability in a corpus analysis tool. International Journal of Corpus Linguistics, 17(3), 380\u2013409. https:\/\/doi.org\/10.1075\/ijcl.17.3.04har","journal-title":"International Journal of Corpus Linguistics"},{"key":"9863_CR21","doi-asserted-by":"crossref","unstructured":"Kim, Y., Lee, J., Lee, E. B., & Lee, J. H. (2020). Application of Natural Language Processing (NLP) and Text-Mining of Big-Data to Engineering-Procurement-Construction (EPC) Bid and Contract Documents. Paper presented at the CDMA 2020: 6th Conference on Data Science and Machine Learning Applications, Riyadh, Saudi Arabia.","DOI":"10.1109\/CDMA47397.2020.00027"},{"key":"9863_CR22","doi-asserted-by":"crossref","unstructured":"Koester, A. (2022). Building small specialised corpora. In O. K. Anne, & M. J. McCarthy (Eds.), The Routledge handbook of Corpus linguistics (second ed., pp. 48\u201361). Routledge.","DOI":"10.4324\/9780367076399-5"},{"key":"9863_CR23","doi-asserted-by":"publisher","first-page":"103334","DOI":"10.1016\/j.autcon.2020.103334","volume":"119","author":"H Liu","year":"2020","unstructured":"Liu, H., Wang, G., Huang, T., He, Ping, Skitmore, M., & Luo, X. (2020). Manifesting construction activity scenes via image captioning. Automation in Construction, 119, 103334. https:\/\/doi.org\/10.1016\/j.autcon.2020.103334","journal-title":"Automation in Construction"},{"key":"9863_CR24","doi-asserted-by":"crossref","unstructured":"McEnery, T., & Brookes, G. (2022). Building a written corpus: What are the basics? In O. K. Anne, & M. J. McCarthy (Eds.), The Routledge handbook of Corpus linguistics (second ed.). Routledge.","DOI":"10.4324\/9780367076399-4"},{"key":"9863_CR25","unstructured":"National Natural Language Processing Plan of Israel (2022). Retrieved from https:\/\/nnlp-il.mafat.ai\/"},{"key":"9863_CR26","doi-asserted-by":"crossref","unstructured":"Nguyen, M., Van, Lai, V., Dac, P. B., Veyseh, A., & Nguyen, T. H. (2021). Trankit: A Light-Weight Transformer-based Toolkit for Multilingual Natural Language Processing. Paper presented at the EACL 2021: 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations, Online conference.","DOI":"10.18653\/v1\/2021.eacl-demos.10"},{"key":"9863_CR27","unstructured":"Nivre, J., & de Marneffe, M. C. (2016). Ginter, Filip, Goldberg, Yoav, Haji\u010d, Jan, Manning, Christopher D.,. Zeman, Daniel. Universal Dependencies v1: A Multilingual Treebank Collection. Paper presented at the LREC\u201916: 10th International Conference on Language Resources and Evaluation, Portoro\u017e, Slovenia. https:\/\/aclanthology.org\/L16-1262\/."},{"key":"9863_CR28","unstructured":"Plank, B., & van Noord, G. (2011). Effective Measures of Domain Similarity for Parsing. Paper presented at the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Portland, OR."},{"key":"9863_CR29","doi-asserted-by":"crossref","unstructured":"Reppen, R. (2022). Building a corpus: what are key considerations? In Anne O\u2019Keeffe & Michael J. McCarthy (Eds.), The Routledge Handbook of Corpus Linguistics (2nd Edition ed.).","DOI":"10.4324\/9780367076399-2"},{"key":"9863_CR30","unstructured":"Ritchie, H., Rod\u00e9s-Guirao, Lucas, Mathieu, Edouard, Gerber, Marcel, Ortiz-Ospina, Esteban, Hasell, Joe, & Roser (2024). Max. Population Growth. Retrieved from https:\/\/ourworldindata.org\/population-growth"},{"key":"9863_CR31","unstructured":"Shadar, H. (2014). The Building blocks of public housing: Six decades of Israeli public initiative urban Building [in hebrew]. Ministry of Construction and Housing."},{"issue":"3","key":"9863_CR32","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1080\/1357480032000155132","volume":"8","author":"H Shadar","year":"2003","unstructured":"Shadar, H., & Oxman, R. (2003). Of village and city: Ideology in Israeli public planning. Journal of Urban Design, 8(3), 243\u2013268. https:\/\/doi.org\/10.1080\/1357480032000155132","journal-title":"Journal of Urban Design"},{"key":"9863_CR33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.autcon.2023.105200","volume":"158","author":"A Shamshiri","year":"2024","unstructured":"Shamshiri, A., Ryu, K. Rok, & Park, J. Y. (2024). Text mining and natural Language processing in construction. Automation in Construction, 158, 1\u201315. https:\/\/doi.org\/10.1016\/j.autcon.2023.105200","journal-title":"Automation in Construction"},{"key":"9863_CR34","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1016\/S0264-8377(02)00008-X","volume":"19","author":"M Shoshany","year":"2002","unstructured":"Shoshany, M., & Goldshleger, N. (2002). Land-use and population density changes in Israel\u20141950 to 1990: Analysis of regional and local trends. Land Use Policy, 19, 123\u2013133. https:\/\/doi.org\/10.1016\/S0264-8377(02)00008-X","journal-title":"Land Use Policy"},{"key":"9863_CR35","doi-asserted-by":"crossref","unstructured":"Song, J., Kim, J., & Lee, J. K. (2018). NLP and Deep Learning-based Analysis of Building Regulations to Support Automated Rule Checking System. Paper presented at the ISARC 2018: 35th International Symposium on Automation and Robotics in Construction, Berlin.","DOI":"10.22260\/ISARC2018\/0080"},{"key":"9863_CR36","doi-asserted-by":"crossref","unstructured":"Tsarfaty, R., Seker, Amit, Sadde, S., & Klein, S. (2019). What\u2019s wrong with Hebrew NLP? And how to make it right. Paper presented at the 2019 EMNLP and the 9th IJCNLP, Hong Kong.","DOI":"10.18653\/v1\/D19-3044"},{"key":"9863_CR37","unstructured":"Weinreb, A., & Chernichovsky, D. (2018). Israel\u2019s Exceptional Fertility. Retrieved from https:\/\/www.taubcenter.org.il\/en\/research\/israels-exceptional-fertility\/"},{"key":"9863_CR38","doi-asserted-by":"publisher","first-page":"104059","DOI":"10.1016\/j.autcon.2021.104059","volume":"134","author":"C Wu","year":"2022","unstructured":"Wu, C., Li, X., Guo, Yuanjun, Wang, Jun, Ren, Z., Wang, M., & Yang, Z. (2022). Natural Language processing for smart construction: Current status and future directions. Automation in Construction, 134, 104059. https:\/\/doi.org\/10.1016\/j.autcon.2021.104059","journal-title":"Automation in Construction"},{"key":"9863_CR39","doi-asserted-by":"crossref","unstructured":"Zeldes, A. (2021). Howell, Nick, Ordan, Noam, & Ben Moshe, Yifat. A second wave of UD Hebrew treebanking and cross-domain parsing. Paper presented at the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations, Online conference.","DOI":"10.18653\/v1\/2022.emnlp-main.292"},{"key":"9863_CR40","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1016\/j.autcon.2016.08.027","volume":"73","author":"J Zhang","year":"2017","unstructured":"Zhang, J., & El-Gohary, N. M. (2017). Integrating semantic NLP and logic reasoning into a unified system for fully-automated code checking. Automation in Construction, 73, 45\u201357. https:\/\/doi.org\/10.1016\/j.autcon.2016.08.027","journal-title":"Automation in Construction"},{"key":"9863_CR41","doi-asserted-by":"publisher","first-page":"105316","DOI":"10.1016\/j.autcon.2024.105316","volume":"160","author":"Y Zhong","year":"2024","unstructured":"Zhong, Y., & Goodfellow, S. D. (2024). Domain-specific Language models pre-trained on construction management systems corpora. Automation in Construction, 160, 105316. https:\/\/doi.org\/10.1016\/j.autcon.2024.105316","journal-title":"Automation in Construction"}],"container-title":["Language Resources and Evaluation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10579-025-09863-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10579-025-09863-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10579-025-09863-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T05:14:40Z","timestamp":1765257280000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10579-025-09863-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,15]]},"references-count":41,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["9863"],"URL":"https:\/\/doi.org\/10.1007\/s10579-025-09863-y","relation":{},"ISSN":["1574-020X","1574-0218"],"issn-type":[{"type":"print","value":"1574-020X"},{"type":"electronic","value":"1574-0218"}],"subject":[],"published":{"date-parts":[[2025,9,15]]},"assertion":[{"value":"18 February 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 June 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 September 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}